towerforge/claude-agents
Lists the Claude Code subagents on disk and shows which ones are running, what they were asked to do, how long they worked and the tokens they used.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit towerforge/claude-agents/.claude ./rig-claude-agents # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/backend.md https://raw.githubusercontent.com/towerforge/claude-agents/main/.claude/agents/backend.md $ curl -fsSL --create-dirs -o .claude/agents/data.md https://raw.githubusercontent.com/towerforge/claude-agents/main/.claude/agents/data.md $ curl -fsSL --create-dirs -o .claude/agents/docs.md https://raw.githubusercontent.com/towerforge/claude-agents/main/.claude/agents/docs.md $ curl -fsSL --create-dirs -o .claude/agents/frontend.md https://raw.githubusercontent.com/towerforge/claude-agents/main/.claude/agents/frontend.md $ curl -fsSL --create-dirs -o .claude/agents/visual.md https://raw.githubusercontent.com/towerforge/claude-agents/main/.claude/agents/visual.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Subagents (5)
| backend | Núcleo de claude-agents — el cruce entre definiciones e invocaciones (src/status.rs), la orquestación de main() (raíces, ventana, cruce, orden de filas, errores), el bucle de eventos y el hilo de lect |
| data | Datos de claude-agents — lo que la herramienta lee del disco y de los procesos, y en qué forma. Definiciones de agentes (.claude/agents/*.md y su frontmatter), transcripciones de Claude Code (~/.claud |
| docs | Documentación de claude-agents. Úsalo tras cualquier cambio de comportamiento, flags, formato leído, configuración o comandos, y cuando se pida revisar la documentación. Mantiene al día README.md, CLA |
| frontend | Interfaz de claude-agents — el contrato con quien la usa en la terminal. Flags, valores por defecto y textos de ayuda de clap (struct Cli en src/main.rs), qué columnas y líneas salen y en qué orden, c |
| visual | Aspecto de claude-agents — cómo se ve la tabla y la pantalla en la terminal. La pantalla ratatui (src/tui/view.rs: cabecera, secciones con regla, filas con ❯ y número, ficha, pie) y sus colores (src/t |
Similar rigs
diegosvart/main-base-claude-code
Claude Code project template with inception agent, specialized subagents, and quality-enforced workflows. From idea to codebase in one structured discovery session.
Orchestrator 52 tok · · Q15
eugeek/claude-config-tdd
Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment
Orchestrator 5.8k tok · · Q29
Caezarr/Vulcan
Vulcan: Features shipping
Orchestrator 3.0k tok · · Q0
YounusHussain9/claude-agent-workspace
Multi-repo workspace for Claude Code: plain-language requests, specialist AI agents, approval gates and safety hooks.
Fort Knox 2.0k tok · · Q54